- Artificial Analysis Intelligence Index v4.3.2 24.1
- AutomationBench-AA (Artificial Analysis score quoted by Upstage) 22.3
- τ³-Banking (a separate evaluation, printed as 47.2) 47.2
- AA-LCR (Artificial Analysis score quoted by Upstage) 83.3
- SciCode (Artificial Analysis score quoted by Upstage) 47.6
- Humanity’s Last Exam (Artificial Analysis score quoted by Upstage) 25.8
Solar Mini 4
Solar Mini 4 places in the top three on 2 benchmarks.
6
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Upstage Oct 2026 Solar Mini 4
Closed weights Small
No Epoch Capabilities Index score yet
- SciCode 47.6% #15 /47
- AA-LCR 1.1 83.3% #2 /5
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AA-LCR 1.1 | 83.3% | #2 of 5 | Model card | |
| Humanity's Last Exam | 25.8% | #84 of 147 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SciCode | 47.6% | #15 of 47 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| τ³-bench Banking | 47.2% | #2 of 20 | Model card | |
| AutomationBench | 22.3% | #34 of 41 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index v4.3 | 24.1 | #4 of 4 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.